{"id":"https://openalex.org/W4285226558","doi":"https://doi.org/10.1007/978-3-031-06516-3_15","title":"A Digitization Pipeline for Mixed-Typed Documents Using Machine Learning and Optical Character Recognition","display_name":"A Digitization Pipeline for Mixed-Typed Documents Using Machine Learning and Optical Character Recognition","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285226558","doi":"https://doi.org/10.1007/978-3-031-06516-3_15"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-06516-3_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-06516-3_15","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://resolver.sub.uni-goettingen.de/purl?gro-2/136878","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028311447","display_name":"Tizian Matschak","orcid":"https://orcid.org/0000-0002-6130-2366"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Tizian Matschak","raw_affiliation_strings":["University of Goettingen, Wilhelmsplatz 1, 37073, Goettingen, Germany"],"affiliations":[{"raw_affiliation_string":"University of Goettingen, Wilhelmsplatz 1, 37073, Goettingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055765992","display_name":"Florian Rampold","orcid":"https://orcid.org/0000-0002-7755-1279"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Rampold","raw_affiliation_strings":["University of Goettingen, Wilhelmsplatz 1, 37073, Goettingen, Germany"],"affiliations":[{"raw_affiliation_string":"University of Goettingen, Wilhelmsplatz 1, 37073, Goettingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066670841","display_name":"Malte Hellmeier","orcid":"https://orcid.org/0000-0002-2095-662X"},"institutions":[{"id":"https://openalex.org/I4210163630","display_name":"Fraunhofer Institute for Software and Systems Engineering","ror":"https://ror.org/058kjq542","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210163630","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Malte Hellmeier","raw_affiliation_strings":["Fraunhofer ISST, Emil-Figge-Stra\u00dfe 91, 44227, Dortmund, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer ISST, Emil-Figge-Stra\u00dfe 91, 44227, Dortmund, Germany","institution_ids":["https://openalex.org/I4210163630"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021978264","display_name":"Christoph Prinz","orcid":"https://orcid.org/0000-0001-9032-8699"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Prinz","raw_affiliation_strings":["University of Goettingen, Wilhelmsplatz 1, 37073, Goettingen, Germany"],"affiliations":[{"raw_affiliation_string":"University of Goettingen, Wilhelmsplatz 1, 37073, Goettingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066980618","display_name":"Simon Trang","orcid":"https://orcid.org/0000-0002-4784-4038"},"institutions":[{"id":"https://openalex.org/I74656192","display_name":"University of G\u00f6ttingen","ror":"https://ror.org/01y9bpm73","country_code":"DE","type":"education","lineage":["https://openalex.org/I74656192"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Trang","raw_affiliation_strings":["University of Goettingen, Wilhelmsplatz 1, 37073, Goettingen, Germany"],"affiliations":[{"raw_affiliation_string":"University of Goettingen, Wilhelmsplatz 1, 37073, Goettingen, Germany","institution_ids":["https://openalex.org/I74656192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028311447"],"corresponding_institution_ids":["https://openalex.org/I74656192"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.1409,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.48563126,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"195","last_page":"207"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9685999751091003,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.91956627368927},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7703500986099243},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.7648998498916626},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.7246678471565247},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6382665038108826},{"id":"https://openalex.org/keywords/character-recognition","display_name":"Character recognition","score":0.4219758212566376},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3936326503753662},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37170082330703735},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10450604557991028},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10163137316703796},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08133989572525024},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0623323917388916}],"concepts":[{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.91956627368927},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7703500986099243},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.7648998498916626},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.7246678471565247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6382665038108826},{"id":"https://openalex.org/C2987247673","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Character recognition","level":3,"score":0.4219758212566376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3936326503753662},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37170082330703735},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10450604557991028},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10163137316703796},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08133989572525024},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0623323917388916},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-031-06516-3_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-06516-3_15","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:publica.fraunhofer.de:publica/419796","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/419796","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"},{"id":"pmh:oai:publications.goettingen-research-online.de:2/136878","is_oa":true,"landing_page_url":"https://resolver.sub.uni-goettingen.de/purl?gro-2/136878","pdf_url":null,"source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bookPart"}],"best_oa_location":{"id":"pmh:oai:publications.goettingen-research-online.de:2/136878","is_oa":true,"landing_page_url":"https://resolver.sub.uni-goettingen.de/purl?gro-2/136878","pdf_url":null,"source":{"id":"https://openalex.org/S4306401634","display_name":"GoeScholar  The Publication Server of the Georg-August-Universit\u00e4t G\u00f6ttingen (Georg-August-Universit\u00e4t G\u00f6ttingen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210122495","host_organization_name":"Asklepios Klinik St. Georg","host_organization_lineage":["https://openalex.org/I4210122495"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/bookPart"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1276866904","https://openalex.org/W1967238710","https://openalex.org/W2029340218","https://openalex.org/W2055075080","https://openalex.org/W2055408190","https://openalex.org/W2096451472","https://openalex.org/W2136922540","https://openalex.org/W2151071493","https://openalex.org/W2159838424","https://openalex.org/W2159877218","https://openalex.org/W2537487445","https://openalex.org/W2560581058","https://openalex.org/W2565019508","https://openalex.org/W2599954636","https://openalex.org/W2767711919","https://openalex.org/W2782536276","https://openalex.org/W2786952617","https://openalex.org/W2810884344","https://openalex.org/W2901285161","https://openalex.org/W2901465038","https://openalex.org/W2969283397","https://openalex.org/W2973363064","https://openalex.org/W2982167926","https://openalex.org/W3045882047","https://openalex.org/W3049493786","https://openalex.org/W3109694770","https://openalex.org/W3151685851","https://openalex.org/W3184906676","https://openalex.org/W4244841724"],"related_works":["https://openalex.org/W1991513203","https://openalex.org/W2892704491","https://openalex.org/W3178467699","https://openalex.org/W4312612713","https://openalex.org/W2106936331","https://openalex.org/W2042634493","https://openalex.org/W1985626581","https://openalex.org/W2100798736","https://openalex.org/W2321008539","https://openalex.org/W2728450881"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
